ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

wechat article formatter pro

v1.0.0

微信公众号智能排版引擎。输入草稿，AI 将自动润色、补全 Markdown 标签，并根据用户指定的主题色生成最终排版。

⭐ 1· 204·0 current·0 all-time
by@tlgzs
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description, SKILL.md workflow, and included Python modules (skill_entry.py and wechat_template_generator.py) all focus on converting a Markdown draft to themed HTML using the bundled CSS themes. Nothing requests unrelated services or credentials.
ℹ
Instruction Scope
SKILL.md instructs the agent to produce/overwrite draft_article.md in the current directory and to run `python3 skill_entry.py draft_article.md <theme>`. That is within the stated purpose, but it will write files in the working directory (and create an output_articles/ folder) — users should be aware it may overwrite an existing draft_article.md if present.
✓
Install Mechanism
No external install or remote downloads; code is included in the bundle. The only runtime dependency is the Python 'markdown' package which is not declared in metadata — there is no high-risk install step or external URL fetch.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. The code performs only local file reads/writes and local Markdown-to-HTML conversion, matching the purpose.
✓
Persistence & Privilege
always is false and the skill does not attempt to modify other skills or global agent settings. It only writes generated HTML to output_articles/ in the current workspace.
Assessment
This skill appears coherent and focused: it converts drafted Markdown into a themed HTML file using bundled CSS. Before installing/using it: (1) ensure Python 3 and the Python 'markdown' package are available (the skill does not declare this dependency); (2) run it in a directory where writing draft_article.md and creating output_articles/ is acceptable (it may overwrite draft_article.md if present); (3) review the included Python files if you require extra assurance — they perform only local file I/O and HTML generation and make no network calls or credential accesses; (4) for extra safety, run the skill in an isolated/sandbox environment if the input or execution context is untrusted.

Like a lobster shell, security has layers — review code before you run it.

latestvk9742n9b26m02r42ppr4rpte3582ydyt

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments